paper-with-me

Papers

BEACON: Behavioral Entropy Aggregation for Cross-Model Hallucination Detection in Large Language Models

2026-04-20 · Naveen Bera, Pulijala Sai Nikhila, Kondaguduru Abhiram, Shaik Gayaz Ali, Shoaib Sadiq Salehmohamed, Shaik Mohammed Omar, Jinal Prashant Thakkar, Hansika Aredla, Shalmali Ayachit arxiv

Hallucination in large language models (LLMs), defined as the generation of factually incorrect or unsupported content, remains a critical barrier to reliable deployment. We present BEACON (Behavioral Entropy Aggregation for Cross-model hallucination detectiON), a black-box hallucination detection framework that operates purely on model outputs without requiring access to internal representations or external knowledge bases. BEACON extracts a 31-dimensional feature vector from structured multi-pass generation, integrating NLI-based semantic entropy, embedding geometry, chain-of-thought consistency, and paraphrase stability signals. A gradient-boosted classifier trained on 7,617 labeled examples across seven benchmarks achieves 0.8123 +/- 0.0102 AUROC (95% CI: 0.7632-0.8251), outperforming standalone semantic entropy (+0.2298) and SelfCheckGPT-style consistency baselines (+0.2457). Feature importance analysis shows that hallucination is inherently multi-dimensional, requiring combined uncertainty signals. An efficient 5-call variant achieves 0.7795 AUROC, enabling practical deployment across black-box LLM APIs.

📄 PDF Abstract BibTeX arXiv:2606.07528

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Importance

Similar Papers 제목 키워드 기반

BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data

2026-05-11 · Ishpuneet Singh, Gursmeep Kaur, Uday Pratap Singh Atwal, Guramrit Singh 외 arxiv

Continuous authentication in high-stakes digital environments requires datasets with fine-grained behavioral signals under realistic cognitive and motor demands. But current benchmarks are often limited by small scale, u…

Representation Learning

BEACON: Behavioral Malware Classification with Large Language Model Embeddings and Deep Learning

2025-09-18 · Wadduwage Shanika Perera, Haodi Jiang arxiv

Malware is becoming increasingly complex and widespread, making it essential to develop more effective and timely detection methods. Traditional static analysis often fails to defend against modern threats that employ co…

Malware ClassificationMalware Detection

BEACON: A Unified Behavioral-Tactical Framework for Explainable Cybercrime Analysis with Large Language Models

2025-12-06 · Arush Sachdeva, Rajendraprasad Saravanan, Gargi Sarkar, Kavita Vemuri 외 arxiv

Cybercrime increasingly exploits human cognitive biases in addition to technical vulnerabilities, yet most existing analytical frameworks focus primarily on operational aspects and overlook psychological manipulation. Th…

Multi-Label Classification

The Map of Misbelief: Tracing Intrinsic and Extrinsic Hallucinations Through Attention Patterns

2025-11-13 · Elyes Hajji, Aymen Bouguerra, Fabio Arnez arxiv

Large Language Models (LLMs) are increasingly deployed in safety-critical domains, yet remain susceptible to hallucinations. While prior works have proposed confidence representation methods for hallucination detection, …

Entropy-Dominated Temporal Vocal Dynamics as Digital Biomarkers for Depression Detection

2026-04-29 · Himadri S Samanta arxiv

Automated depression detection often relies on static aggregation of conversational signals, potentially obscuring clinically meaningful behavioral dynamics. We investigated whether entropy-driven temporal biomarkers imp…